AmirhosseinHonardoust/Financial-Fraud-Risk-Engine
A complete end-to-end fraud detection system for financial transactions, featuring data pipelines, cost-sensitive ML modeling, explainability with SHAP, threshold optimization, batch scoring, and an interactive Streamlit dashboard. Designed to simulate real-world fintech fraud-risk workflows.
This project helps financial institutions and fintech companies automatically identify suspicious transactions in real-time. It takes raw transaction data (like amount, type, and risk scores) and outputs a fraud probability and a 'fraud flag' for each transaction. Financial crime analysts, risk managers, and compliance officers would use this to prioritize investigations and reduce financial losses from fraud.
Use this if you need an end-to-end system to detect financial fraud, including data processing, explainable models, and an interactive dashboard for analysts.
Not ideal if you're looking for a simple model notebook or a solution for non-financial fraud types.
Stars
18
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 04, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AmirhosseinHonardoust/Financial-Fraud-Risk-Engine"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
GoogleCloudPlatform/fraudfinder
Fraudfinder: A comprehensive lab series on how to build a real-time fraud detection system on...
benedekrozemberczki/awesome-fraud-detection-papers
A curated list of data mining papers about fraud detection.
jube-home/aml-fraud-transaction-monitoring
Open source AML and Fraud Detection using Machine Learning for Real-Time Transaction Monitoring
aws-solutions-library-samples/fraud-detection-using-machine-learning
Setup end to end demo architecture for predicting fraud events with Machine Learning using...
curiousily/Credit-Card-Fraud-Detection-using-Autoencoders-in-Keras
iPython notebook and pre-trained model that shows how to build deep Autoencoder in Keras for...